Combinatorial designs in multiple faults localization for battlefield networks

We present an application of combinatorial designs and variance analysis to correlating events in the midst of multiple network faults. The network fault model is based on the probabilistic dependency graph that accounts for the uncertainty about the state of network elements. Orthogonal arrays help reduce the exponential number of failure configurations to a small subset on which further analysis is performed. The preliminary results show that statistical analysis can pinpoint the probable causes of the observed symptoms with high accuracy and significant level of confidence. An example demonstrates how multiple soft link failures are localized in MIL-STD 188-220´s datalink layer to explain the end-to-end connectivity problems in the network layer This technique can be utilized for the networks operating in an unreliable environment such as wireless and/or military networks.